Paper published in the Journal of Medical Internet Research: Doctors advocate the use of routine clinical data for medical research for the practical use of artificial intelligence in healthcare

Image source: © istockphoto.com/izzetugutmen

Artificial intelligence (AI) and adaptive learning systems are creating completely new treatment methods in medicine. May it evaluating data, recognizing patterns or comparing symptoms. The increasing development goes hand in hand with enormous expectations for the progress of medical care. The University Hospital RWTH Aachen, consortium partner of the SMITH Consortium of the Medical Informatics Initiative, conducted a web-based survey on the requirements and expectations of physicians for the use of future medical applications in health care. The results have now been published in the Journal of Medical Internet Research.

Physicians from all medical disciplines at eight university hospitals of the SMITH Consortium were surveyed. The study also investigated the attitudes towards the secondary use of patient data for biomedical and medical research, e.g. to develop algorithms for machine learning. A total of 303 persons took part in the online survey. In general, the medical staff in inpatient care are positive about the use of most AI applications in medicine. Over 90 percent of the participating physicians assume that the future of medicine will be shaped by a mix of human and artificial intelligence, but at the same time demand a scientific evaluation of AI-based systems before they are implemented in everyday clinical practice.

Availability and simplified access to large, clinical research databases is a fundamental requirement for AI development in medicine. 80 percent of the physicians surveyed were in favor of integrating clinical routine care with medical research in order to optimize patient care as well as biomedical and medical research in the long term. Initiatives such as the German Medical Informatics Initiative, the EOSC (European Open Science Cloud) and the FAIR Data Principles (findable, accessible, interoperable and reusable) create the conditions for research and care to move closer together. In the long term, this will lead to improved analysis of clinical data and more accurate diagnosis and treatment decisions for patients.

To the publication:

Maassen O, Fritsch S, Palm J, Deffge S, Kunze J, Marx G, Riedel M, Schuppert A, Bickenbach J (2021) Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey. J Med Internet Res. 2021;23(3): e26646. doi: 10.2196/26646

Promoting young researchers: Announcement of new scholarships for the Master’s program in Medical Data Science at the RWTH Aachen International Academy

Image source: © istockphoto.com/Halfpoint

This year, the RWTH Aachen International Academy announces the following scholarship offers for the postgraduate, part-time and interprofessional Master’s program “Medical Data Science (M.Sc.)” for the winter semester 2021/22:

  • 2 scholarships for the promotion of young researchers
  • 2 scholarships for project staff within the SMITH-Consortium / at SMITH-Institutions
  • 2 scholarships for employees/students of the RWTH Aachen University and the RWTH University Hospital

The study program focuses on the rapidly advancing digitization in healthcare. Large amounts of data from medicine and healthcare are ready to be used for personalized diagnostics and individual therapy. This requires the training of experts who work integratively at the disciplinary interface of medicine and informatics. The master’s program is aimed at graduates from the fields of computer science, mathematics and natural sciences with specific (medical informatics) professional experience.

The funding is intended to support, among others, young academics at the beginning of their professional career as well as SMITH project staff. The deadline for submitting the complete scholarship application documents is May 15, 2021.

Further information on the application, admission requirements and the Medical Data Science M.Sc. program can be found here: www.master-medical-data-science.de

Contact: RWTH Aachen International Academy | E-Mail: mds@academy.rwth-aachen.de

Uniklinik RWTH Aachen begins intervention phase in the HELP Use Case

Image source: © UKJ/Schroll

On February 1, 2021, the first units of the University Hospital RWTH Aachen, which are involved in the HELP Study, have moved from the control phase to the intervention phase. The clinical Use Case HELP of the SMITH-Consortium is dedicated to responsible antibiotic therapy in staphylococcal bloodstream infections. The HELP App, developed for this purpose under the leadership of the University Hospital Jena, supports the diagnostic and therapeutic procedure. Guideline-based, the mobile application provides the attending physicians with information on the next diagnostic and therapeutic steps and is thus intended to facilitate the work of infectious diseases specialists in normal and intensive care units. In addition to a direct improvement in patient care, this also contributes indirectly to the avoidance of antibiotic-related multi-resistant infections and to the optimization of inpatient consultation by infectiologists.

The HELP App has already been in use at the University Hospital site in Jena since mid-August 2020 and in Leipzig since October. With the start of the intervention phase in Aachen, the HELP App will now be integrated into everyday clinical practice in a two-month rhythm on 10 intensive care units and 14 normal units. The data required for the study is provided by the participating Data Integration Centers (DIC) in an interoperable data format based on FHIR and the Medical Informatics Initiative (MII) core data set. The university hospitals of Aachen, Essen, Halle, Jena and Leipzig are collaborating in the study.

More information on the HELP study can be found here.

SMITH Online Closed Meeting | February 2021

Image source: © SMITH-Geschäftsstelle

On February 24 – 25, 2021, the quarterly closed meeting of the SMITH Consortium took place. 131 project staff members and representatives of the consortium management discussed and agreed on the current project statuses in a two-day web conference. The preparations for the audit, the development of the clinical Use Cases HELP and ASIC as well as the strengthening of teaching were assessed as particularly positive in the reports of the working groups.

The project auditing planned and commissioned by the Federal Ministry of Education and Research (BMBF) could be tested at all sites through friendly audits. In intensive coordination between the quality management and the interoperability workgroup, 22 concepts were developed that serve as preparation for the sites.

In the clinical use cases, the roll-out of the HELP and ASIC App could be continued at further university hospitals. At the present time, the University Hospitals of Jena, Leipzig and Aachen are working with the HELP App. 3,676 patients have been included in the HELP Study by the participating sites. The ASIC App is used in clinical care at the University Hospitals of Aachen and Jena. 8,787 patients were recorded by the eight sites participating in ASIC. HELP and ASIC thus make a significant contribution to improving individual patient care in infection and intensive care medicine at the participating sites.

To strengthen education, training, further education and to consolidate the deployment of specialist staff at the Data Integration Centers (DIC) planned throughout Germany, new professorships in the field of Medical Data Science will be established at the University Hospitals in Essen, Hamburg-Eppendorf and Halle. Three more junior research groups are being planned. In addition, the steering group and the technical project management werde introduced at the beginning of 2020 as new organizational units in the consortium. Project progress and course are coordinated by both units in cooperation with the SMITH Office.

DVMD Focus on February 25, 2021: Lecture on the part-time Master’s program in Medical Data Science at RWTH Aachen University

Image source: © istockphoto.com/Jovanmandic

The German Federal Ministry of Education and Research (BMBF) is funding the development of new courses of study as part of the Medical Informatics Initiative to thus enabling the digital transformation of the healthcare sector to take place and to be staffed with qualified personnel.

In this context, the Medical Faculty of RWTH Aachen University, in cooperation with the RWTH International Academy, has been offering the Master’s program in Medical Data Science in a blended learning format at the SMITH-Location in Aachen since the winter semester 2020/21.

In the first session of its new event series “DVMD Focus”, the Professional Association for Documentation and Information Management in Medicine (DVMD) will thematize the development of new courses of study to attract specialists for the digital transformation in healthcare. On February 25, 2021, a number of concepts will be presented under the title “Innovative Concepts for Online-Based Teaching”, including the Medical Data Science degree program at RWTH Aachen University:

Date: February 25, 2021 | 05:00 pm

Title: Part-time Master in Medical Data Science – a SMITH-Consortium degree program in blended learning format

Speakers:

  • Dr. Ulrike Schemmann – Head of the Department of Education in Medical Informatics, Teaching Coordinator SMITH | Institute of Medical Informatics | Uniklinik RWTH Aachen
  • Prof. Dr. Rainer Röhrig – Director of the Institute for Medical Informatics | Uniklinik RWTH Aachen
  • Prof. Dr. Cord Spreckelsen – Professor of Medical Informatics | Institute of Medical Statistics, Computer Science and Data Sciences (IMSID) | University Hospital Jena

More information about the lecture can be found here.

Further information events on the Medical Data Science program at RWTH Aachen University:

In regular online info events, Prof. Dr. med. Rainer Röhrig (scientific director) and Dr. Ulrike Schemmann (teaching coordinator) present the structure and contents of the part-time master’s program “Medical Data Science”. All dates and access data can be found on the website of the study program.

Improved analysis of treatment data in medical research | New software makes FHIR resources accessible for statistical software

Image source: © istockphoto.com/wutwhanfoto

The HL7 FHIR standard data format defined by the Medical Informatics Initiative (MII) is ideally suited for interoperable data exchange and storage. The possibilities for statistical analysis, on the other hand, are limited. To ensure improved analysis of treatment data, the fhircrackr software was developed as part of the MII Use Case POLAR by the University of Leipzig and the University Hospital Jena, which are members of the SMITH consortium.

The Medical Informatics Initiative (MII) is working with numerous partners to make routinely collected treatment data from healthcare usable for medical research. For this purpose, the MII has agreed on the data format HL7 FHIR Standard for the implementation of the core data set. This is a format that processes heterogeneous data in an interoperable manner, i.e. seamlessly merges them. FHIR data are optimally adapted for the interoperable exchange and storage of medical data. However, they are less suitable for statistical analysis. The FHIR standard stores data in individual, nested and interlinked resources, rather than in tabular structures. Common statistical methods rely precisely on these structures.

To solve the problem, the software fhircrackr was developed as part of the MII Use Case POLAR by the University of Leipzig and the University Hospital Jena, which are members of the SMITH consortium. fhircrackr allows the user to access a FHIR server using the statistical software and programming language R and to download data from there. The downloaded data can then be converted into tabular form and processed for statistical analysis. In the POLAR use case, which deals with health risks in patients with polymedication, medication data available in FHIR can thus be derived from the data integration centers (DIZ) and converted into tables by fhircrackr. On this basis, arbitrary aggregations of the data are possible.

hircrackr was first published on CRAN (Comprehensive R Archive Network) in July 2020. CRAN is a public online archive for R packages that tests and makes package code freely available. In addition, fhircrackr is being developed open source under the software management service Github. As one of the first solutions for transforming FHIR data into tables, this has been very well received throughout the MII and will be used equally in SMITH use cases such as HELP and PHEP and cross-cutting use cases such as POLAR and CORD.

Related links:

CRAN: https://cran.r-project.org/web/packages/fhircrackr/index.html
Github: https://github.com/POLAR-fhiR/fhircrackr

Explanatory video illustrates consent process and goals of Medical Informatics Initiative

Image source: © istockphoto.com/art159

Press Release from Medical Informatics Initiative TMF e. V. | 09.09.2020

The mission of the Medical Informatics Initiative (MII) of the Federal Ministry of Education and Research (BMBF) is to make data captured during routine healthcare treatment available for medical research. This will enable improvements in treatment, diagnostics and prevention. And it requires informed consent on the part of patients to the use of their data for research purposes. With immediate effect, patients are now asked upon admission to university hospitals whether they agree to their treatment data being used, in pseudonymised form, for medical research. Against this backdrop, MII has developed a video which clearly explains and visualises the goals of the nationwide initiative and the in-hospital consent process.

Video on YouTube

To the Press Release from Medical Informatics Initiative TMF e. V. | 09.09.2020

Targeted antibiotic therapy | SMITH-Consortium starts HELP Study at Jena University Hospital

The HELP App developed by the SMITH-Consortium provides medical personnel rapid information and recommendations for responsible antibiotic therapy in staphylococcal bloodstream infections. The HELP App was implemented as part of the study in mid-August at the University Hospital Jena (UKJ) and will be used at four additional participating university hospitals by the end of the year.

Any use of antibiotics can promote the development of resistance. It is therefore important to use antibiotics in a targeted and responsible manner in order to limit overuse and under-use. The focus is the balance between an appropriate reduction of antibiotics and their timely use.

A prime example of this is bloodstream infections, which are a widespread problem in hospitals. Bloodstream infections including sepsis are one of the greatest challenges for diagnostics and therapy. Unjustified antibiotics usage promotes the development of resistance and in turn increases the risk of drug-related side effects.

The mobile application HELP of the SMITH-Consortium serves as a digital manual for the treatment of patients with a positive staphylococci blood culture. In accordance with guidelines, the app provides the treating physicians with information on the next diagnostic and therapeutic steps and thus facilitates the work of infectious disease specialists in normal and intensive care units. In addition to a direct improvement in patient care, it also contributes indirectly to the prevention of antibiotic-related multidrug resistance and to the optimization of inpatient consultation by infectiologists. The data required for the study will be provided by the participating data integration centers (DIC) in an interoperable data format based on FHIR and the core data set of the Medical Informatics Initiative (MII). The MII decided that the the international HL7 standard FHIR would be the data format in July 2019.

The university hospitals in Aachen, Essen, Halle, Jena and Leipzig are participating in the study. In the course of the study, the HELP App will be used in additional university hospitals. The SMITH-Locations Leipzig and Aachen will be integrated into the study next.

German Interdisciplinary Association for Intensive Care and Emergency Medicine (DIVI) pledges support to SMITH-Consortium

The German Interdisciplinary Association for Intensive Care and Emergency Medicine (DIVI) promotes practical as well as scientific progress in intensive and emergency medicine. With the Use Case ASIC, the SMITH consortium makes an important contribution to this. In a Letter of Intent, DIVI now confirms its interest in a cooperation.

Cooperative and interdisciplinary communication is the basis for strong partnership and cooperation. An active exchange of knowledge benefits the specialist disciplines and thus the patient. With the Use Case ASIC, the SMITH consortium promotes the improvement of patient care by using already existing clinical routine data. This is to be demonstrated using the example of the therapy of patients with acute lung failure, or ARDS (acute respiratory distress syndrome), a disease that still kills about 40 percent of all patients today. In addition, many of the corona patients receiving intensive care suffer from ARDS during treatment, although numerous monitoring systems continuously monitor the patients’ most important vital functions. Especially the early forms of ARDS are often only detected when the lung function has further deteriorated.

The ASIC App, developed as part of the Use Case ASIC, counteracts this by ensuring continuous electronic monitoring of relevant ventilation parameters and alerting the attending physicians to potential ARDS even before the patient’s condition has changed critically. With an earlier diagnosis and a therapy in line with guidelines, valuable time in the treatment of patients can be gained, which can save more lives.

The German Interdisciplinary Association for Intensive Care and Emergency Medicine (DIVI) focuses on science, practice and research in intensive and emergency medicine and has now officially expressed its support for SMITH in a letter of intent. With the automation of intensive care monitoring, the SMITH Consortium’s Use Case ASIC makes a decisive contribution to quality assurance in intensive care medicine.

Further information on the German Interdisciplinary Association for Intensive Care and Emergency Medicine can be found here.

Use of the ASIC App is being expanded to intensive care units

Almost one year after the start of the control phase, the quality approvement strategy in the ASIC Use Case of the SMITH Consortium has been launched. For this the ASIC App will now be made available and used step by step on all participating intensive care units.

The focus of the Use Case ASIC is on intensive care patients with acute lung failure (ARDS – acute respiratory distress syndrome), a disease that still kills about 40 percent of all patients. The aim is to make the diagnosis as quickly as possible by using already documented, routine clinical data and to achieve better treatment by following the recommendations of relevant guidelines. 

Ventilation parameters are taken from the patient data management system via the ASIC App and examined for the potential presence of ARDS. Suspected cases of ARDS are immediately reported to the treating intensive care physicians via the ASIC app, which is certified as a medical device. This enables an early diagnostic and therapeutic reaction of the treating physicians. If the criteria are met after medical review and the information are confirmed, the app displays the respective severity and the relevant guideline-based therapy recommendations. 

Today, the Clinic for Operative Intensive Medicine and Intermediate Care of the University Hospital RWTH Aachen was the first department to successfully launch the app. The response of the medical colleagues in the intensive care units are consistently positive and acceptance is high. In the course of the next months the next SMITH project partners will start using the ASIC App. This includes the university hospitals of Bonn, Düsseldorf, Halle, Hamburg, Jena, Leipzig and Rostock.